AGI Eval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
AGI Eval English
90.1Score
32
AGI Eval
40.2AGI Eval Score
24
AGI Eval EN
89.4Accuracy
15
AGI Eval
73.4Avg@1 (AGI Eval Reasoning)
12
AGI-Eval Math
94.7Overall Accuracy
11
AGI-Eval
61.2Accuracy
10
AGI Eval English
92.2Score
8
AGI-Eval text-to-image arena 6
0.486ELO Score
6